Replay spoofing countermeasure using autoencoder and siamese networks on ASVspoof 2019 challenge. (November 2020)

• Record Type: Journal Article
• Authors: Adiban, Mohammad; Sameti, Hossein; Shehnepoor, Saeedreza
• Is Part Of: Computer speech & language. Volume 64(2020)
• Publication Date: 2020-11
• Subjects: Spoof detection -- Replay attack -- ASVspoof challenge -- CQCC -- Autoencoder -- Siamese network; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2020.101105
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Employing Constant Q Cepstral Coefficient (CQCC) features to represent each spoof and genuine sample. Using Variational AutoEncoders (VAEs) to transform the extracted CQCC from sparce feature space to latent feature space and compress them to more informative and compressed vectors. Using Siamese Network for the first time to classify the samples based on compressed features from VAE bottleneck. Improving the performance in terms of EER by 10% and t-DCF by 20%, in comparison with baseline system. Abstract: Automatic Speaker Verification (ASV) is authentication of individuals by analyzing their speech signals. Different synthetic approaches allow spoofing to deceive ASV systems (ASVs), whether using techniques to imitate a voice or reconstruct the features. Attackers beat up the ASVs using four general techniques; impersonation, speech synthesis, voice conversion, and replay. The last technique is considered as a common and high potential tool for spoofing purposes since replay attacks are more accessible and require no technical knowledge of adversaries. In this study, we introduce a novel replay spoofing countermeasure for ASVs. Accordingly, we use the Constant Q Cepstral Coefficient (CQCC) features fed into an autoencoder to attain more informative features and to consider the noise information of spoofed utterances for discrimination purpose. Finally, different configurations of the Siamese network are used for the first time in this context for classification. The experiments performed on ASVspoof challenge 2019 dataset using Equal Error Rate (EER) and Tandem Detection Cost Function (t-DCF) as evaluation metrics show that the proposed system improved the results over the baseline by 10.73% and 0.2344 in terms of EER and t-DCF, respectively.